Meta 发布 Muse Spark Open 开放权重模型，8160 亿参数对标 Qwen 和 GLM
Muse Spark Open is Meta's answer to Qwen, GLM, and Kimi in the open-weight race
Meta 放出 8160 亿参数的多模态开放权重模型，能跑视频和音频，还能在 M5 Ultra 上本地跑，直接对标 Qwen 和 Kimi，开源玩家可以看看。
Meta 发布开放权重模型 Muse Spark Open，总参数量 8160 亿。该模型支持文本、图像、视频和音频多模态输入，上下文窗口最长 100 万 token。基准测试成绩大致与 Qwen、GLM、Kimi 等最强开放权重中文模型持平。模型针对 Apple M5 Ultra 芯片做了本地运行优化。
Muse Spark Open is Meta's answer to Qwen, GLM, and Kimi in the open-weight race
Meta's Muse Spark Open is a new open-weight model with 816 billion parameters that processes text, images, video, and audio with up to one million tokens of context. It performs roughly on par with the most capable open-weight Chinese AI models on benchmarks and is optimized to run locally on Apple's M5 Ultra. The article Muse Spark Open is Meta's answer to Qwen, GLM, and Kimi in the open-weight race appeared first on The Decoder .
